PrefLUT：基于成对偏好的可复用且可优化的个性化颜色编辑
PrefLUT: Reusable and Refinable Personalized Color Editing from Pairwise Preferences
查看机构详情
- The University of Sydney（悉尼大学）
- Indiana University（印第安纳大学）
- The University of Hong Kong（香港大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
PrefLUT通过轻量级用户画像和查询条件LUT预测器，实现可复用、可优化的个性化颜色编辑，无需逐用户优化，仅需260字节存储和1.365毫秒/图，并引入PCVP验证协议。
中文摘要 AI 辅助
摄影颜色编辑本质上是个人化的：同一张图像在不同用户看来可能显得过暖、过于柔和或已经令人满意。大多数查找表（LUT）和参考引导方法针对特定外观进行优化，而非从重复的用户选择中建模持久偏好。为解决这一差距，我们提出了PrefLUT，一个可复用且可优化的用户偏好建模框架，用于可部署的3D LUT，将有序的偏好/非偏好图像对编码为轻量级的可复用用户画像，该画像可在查询间复用，并可通过额外的用户偏好对进行优化，无需逐用户优化。查询条件LUT预测器将该画像与每张图像结合，预测LUT潜在向量和编辑强度。身份残差LUT解码器和编辑强度控制器随后生成可导出的3D LUT。在三个数据集上的实验证明了有效的个性化编辑和通用增强。每个量化画像仅需260字节，在RTX 5090 GPU上编辑每张图像耗时1.365毫秒。我们还引入了偏好条件验证协议（PCVP），该评估协议通过控制用户画像、偏好顺序、配对对应关系和查询图像的变化，验证个性化图像编辑是否依赖于用户偏好和查询图像。
英文摘要
Photographic color editing is inherently personal: the same image can appear too warm, too muted, or already satisfactory to different users. Most lookup table (LUT) and reference-guided methods target a specified appearance rather than model persistent preferences from repeated user choices. To address this gap, we introduce PrefLUT, a reusable and refinable user-preference modeling framework for deployable 3D LUTs, encoding ordered preferred/non-preferred image pairs into a lightweight Reusable User Profile that is reused across queries and refined using additional user preference pairs, without per-user optimization. A Query-Conditioned LUT Predictor combines this profile with each image to predict a LUT latent vector and edit strength. An Identity-Residual LUT Decoder and Edit-Strength Controller then produce an exportable 3D LUT. Experiments on three datasets demonstrate effective personalized editing and general-purpose enhancement. Each quantized profile requires only 260 bytes, and editing takes 1.365 ms/image on an RTX 5090 GPU. We also introduce the Preference-Conditioning Verification Protocol (PCVP), an evaluation protocol to verify whether personalized image edits depend on user preferences and the query image through controlled changes to user profiles, preference orders, pair correspondences, and query images.
